traject 3.0.0 → 3.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.travis.yml +3 -4
- data/CHANGES.md +65 -0
- data/README.md +9 -4
- data/doc/indexing_rules.md +5 -6
- data/doc/programmatic_use.md +25 -1
- data/doc/settings.md +4 -0
- data/doc/xml.md +12 -0
- data/lib/traject/indexer.rb +40 -4
- data/lib/traject/indexer/context.rb +45 -0
- data/lib/traject/indexer/step.rb +8 -12
- data/lib/traject/line_writer.rb +36 -4
- data/lib/traject/macros/marc21.rb +2 -2
- data/lib/traject/macros/marc21_semantics.rb +15 -12
- data/lib/traject/macros/nokogiri_macros.rb +9 -3
- data/lib/traject/nokogiri_reader.rb +17 -19
- data/lib/traject/oai_pmh_nokogiri_reader.rb +9 -3
- data/lib/traject/solr_json_writer.rb +167 -29
- data/lib/traject/version.rb +1 -1
- data/lib/translation_maps/marc_languages.yaml +77 -48
- data/test/delimited_writer_test.rb +14 -16
- data/test/indexer/class_level_configuration_test.rb +127 -0
- data/test/indexer/context_test.rb +64 -1
- data/test/indexer/error_handler_test.rb +18 -0
- data/test/indexer/macros/macros_marc21_semantics_test.rb +4 -0
- data/test/indexer/nokogiri_indexer_test.rb +35 -0
- data/test/nokogiri_reader_test.rb +66 -3
- data/test/solr_json_writer_test.rb +175 -7
- data/test/test_support/date_resort_to_264.marc +1 -0
- data/traject.gemspec +4 -4
- metadata +37 -16
@@ -0,0 +1 @@
|
|
1
|
+
01180aam a2200337 a 4500001001000000008004100010015001900051016001800070020002500088020002200113040005900135043001200194050002400206082001400230100003500244245006400279260003800343264003800381264001100419300003600430336002100466336002800487337002500515338002300540504006700563651004000630651005000670651004300720651005600763035002300819a11417842130723t20uu20uuenkb b 001 0 eng d aGBB3854302bnb7 a0164999372Uk a9781849043427 (pbk.) a1849043426 (pbk.) aUKMGBcUKMGBdOCLCOdYDXCPdOCLCOdZWZdOCLCOdCaONFJC aa-ii--- 4aDS485.K25bS64 201504a954.62231 aSnedden, Christopher,eauthor.10aUnderstanding Kashmir and Kashmiris /cChristopher Snedden. 1aLondon :bHurst & Company,c2014. 1aLondon :bHurst & Company,c2015. 4c©2015 axix, 372 pages :bmaps ;c22 cm atext2rdacontent astill image2rdacontent aunmediated2rdamedia avolume2rdacarrier aIncludes bibliographical references (pages 331-355) and index. 0aJammu and Kashmir (India)xHistory. 0aJammu and Kashmir (India)xForeign relations. 0aJammu and Kashmir (India)vBoundaries. 0aJammu and Kashmir (India)xPolitics and government. a(OCoLC-M)858826393
|
data/traject.gemspec
CHANGED
@@ -24,16 +24,16 @@ Gem::Specification.new do |spec|
|
|
24
24
|
spec.add_dependency "concurrent-ruby", ">= 0.8.0"
|
25
25
|
spec.add_dependency "marc", "~> 1.0"
|
26
26
|
|
27
|
-
spec.add_dependency "hashie", "
|
27
|
+
spec.add_dependency "hashie", ">= 3.1", "< 5" # used for Indexer#settings
|
28
28
|
spec.add_dependency "slop", ">= 3.4.5", "< 4.0" # command line parsing
|
29
29
|
spec.add_dependency "yell" # logging
|
30
30
|
spec.add_dependency "dot-properties", ">= 0.1.1" # reading java style .properties
|
31
31
|
spec.add_dependency "httpclient", "~> 2.5"
|
32
|
-
spec.add_dependency "http", "
|
32
|
+
spec.add_dependency "http", ">= 3.0", "< 5" # used in oai_pmh_reader, may use more extensively in future instead of httpclient
|
33
33
|
spec.add_dependency 'marc-fastxmlwriter', '~>1.0' # fast marc->xml
|
34
|
-
spec.add_dependency "nokogiri", "~> 1.
|
34
|
+
spec.add_dependency "nokogiri", "~> 1.9" # NokogiriIndexer
|
35
35
|
|
36
|
-
spec.add_development_dependency
|
36
|
+
spec.add_development_dependency 'bundler', '>= 1.7', '< 3'
|
37
37
|
|
38
38
|
spec.add_development_dependency "rake"
|
39
39
|
spec.add_development_dependency "minitest"
|
metadata
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: traject
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.
|
4
|
+
version: 3.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jonathan Rochkind
|
8
8
|
- Bill Dueber
|
9
|
-
autorequire:
|
9
|
+
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date:
|
12
|
+
date: 2020-07-07 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: concurrent-ruby
|
@@ -43,16 +43,22 @@ dependencies:
|
|
43
43
|
name: hashie
|
44
44
|
requirement: !ruby/object:Gem::Requirement
|
45
45
|
requirements:
|
46
|
-
- - "
|
46
|
+
- - ">="
|
47
47
|
- !ruby/object:Gem::Version
|
48
48
|
version: '3.1'
|
49
|
+
- - "<"
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
version: '5'
|
49
52
|
type: :runtime
|
50
53
|
prerelease: false
|
51
54
|
version_requirements: !ruby/object:Gem::Requirement
|
52
55
|
requirements:
|
53
|
-
- - "
|
56
|
+
- - ">="
|
54
57
|
- !ruby/object:Gem::Version
|
55
58
|
version: '3.1'
|
59
|
+
- - "<"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '5'
|
56
62
|
- !ruby/object:Gem::Dependency
|
57
63
|
name: slop
|
58
64
|
requirement: !ruby/object:Gem::Requirement
|
@@ -119,16 +125,22 @@ dependencies:
|
|
119
125
|
name: http
|
120
126
|
requirement: !ruby/object:Gem::Requirement
|
121
127
|
requirements:
|
122
|
-
- - "
|
128
|
+
- - ">="
|
123
129
|
- !ruby/object:Gem::Version
|
124
130
|
version: '3.0'
|
131
|
+
- - "<"
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '5'
|
125
134
|
type: :runtime
|
126
135
|
prerelease: false
|
127
136
|
version_requirements: !ruby/object:Gem::Requirement
|
128
137
|
requirements:
|
129
|
-
- - "
|
138
|
+
- - ">="
|
130
139
|
- !ruby/object:Gem::Version
|
131
140
|
version: '3.0'
|
141
|
+
- - "<"
|
142
|
+
- !ruby/object:Gem::Version
|
143
|
+
version: '5'
|
132
144
|
- !ruby/object:Gem::Dependency
|
133
145
|
name: marc-fastxmlwriter
|
134
146
|
requirement: !ruby/object:Gem::Requirement
|
@@ -149,28 +161,34 @@ dependencies:
|
|
149
161
|
requirements:
|
150
162
|
- - "~>"
|
151
163
|
- !ruby/object:Gem::Version
|
152
|
-
version: '1.
|
164
|
+
version: '1.9'
|
153
165
|
type: :runtime
|
154
166
|
prerelease: false
|
155
167
|
version_requirements: !ruby/object:Gem::Requirement
|
156
168
|
requirements:
|
157
169
|
- - "~>"
|
158
170
|
- !ruby/object:Gem::Version
|
159
|
-
version: '1.
|
171
|
+
version: '1.9'
|
160
172
|
- !ruby/object:Gem::Dependency
|
161
173
|
name: bundler
|
162
174
|
requirement: !ruby/object:Gem::Requirement
|
163
175
|
requirements:
|
164
|
-
- - "
|
176
|
+
- - ">="
|
165
177
|
- !ruby/object:Gem::Version
|
166
178
|
version: '1.7'
|
179
|
+
- - "<"
|
180
|
+
- !ruby/object:Gem::Version
|
181
|
+
version: '3'
|
167
182
|
type: :development
|
168
183
|
prerelease: false
|
169
184
|
version_requirements: !ruby/object:Gem::Requirement
|
170
185
|
requirements:
|
171
|
-
- - "
|
186
|
+
- - ">="
|
172
187
|
- !ruby/object:Gem::Version
|
173
188
|
version: '1.7'
|
189
|
+
- - "<"
|
190
|
+
- !ruby/object:Gem::Version
|
191
|
+
version: '3'
|
174
192
|
- !ruby/object:Gem::Dependency
|
175
193
|
name: rake
|
176
194
|
requirement: !ruby/object:Gem::Requirement
|
@@ -213,7 +231,7 @@ dependencies:
|
|
213
231
|
- - "~>"
|
214
232
|
- !ruby/object:Gem::Version
|
215
233
|
version: '3.4'
|
216
|
-
description:
|
234
|
+
description:
|
217
235
|
email:
|
218
236
|
- none@nowhere.org
|
219
237
|
executables:
|
@@ -292,6 +310,7 @@ files:
|
|
292
310
|
- test/debug_writer_test.rb
|
293
311
|
- test/delimited_writer_test.rb
|
294
312
|
- test/experimental_nokogiri_streaming_reader_test.rb
|
313
|
+
- test/indexer/class_level_configuration_test.rb
|
295
314
|
- test/indexer/context_test.rb
|
296
315
|
- test/indexer/each_record_test.rb
|
297
316
|
- test/indexer/error_handler_test.rb
|
@@ -323,6 +342,7 @@ files:
|
|
323
342
|
- test/test_support/bad_subfield_code.marc
|
324
343
|
- test/test_support/bad_utf_byte.utf8.marc
|
325
344
|
- test/test_support/date_resort_to_260.marc
|
345
|
+
- test/test_support/date_resort_to_264.marc
|
326
346
|
- test/test_support/date_type_r_missing_date2.marc
|
327
347
|
- test/test_support/date_with_u.marc
|
328
348
|
- test/test_support/demo_config.rb
|
@@ -370,7 +390,7 @@ homepage: http://github.com/traject/traject
|
|
370
390
|
licenses:
|
371
391
|
- MIT
|
372
392
|
metadata: {}
|
373
|
-
post_install_message:
|
393
|
+
post_install_message:
|
374
394
|
rdoc_options: []
|
375
395
|
require_paths:
|
376
396
|
- lib
|
@@ -385,9 +405,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
385
405
|
- !ruby/object:Gem::Version
|
386
406
|
version: '0'
|
387
407
|
requirements: []
|
388
|
-
|
389
|
-
|
390
|
-
signing_key:
|
408
|
+
rubygems_version: 3.0.3
|
409
|
+
signing_key:
|
391
410
|
specification_version: 4
|
392
411
|
summary: An easy to use, high-performance, flexible and extensible metadata transformation
|
393
412
|
system, focused on library-archives-museums input, and indexing to Solr as output.
|
@@ -395,6 +414,7 @@ test_files:
|
|
395
414
|
- test/debug_writer_test.rb
|
396
415
|
- test/delimited_writer_test.rb
|
397
416
|
- test/experimental_nokogiri_streaming_reader_test.rb
|
417
|
+
- test/indexer/class_level_configuration_test.rb
|
398
418
|
- test/indexer/context_test.rb
|
399
419
|
- test/indexer/each_record_test.rb
|
400
420
|
- test/indexer/error_handler_test.rb
|
@@ -426,6 +446,7 @@ test_files:
|
|
426
446
|
- test/test_support/bad_subfield_code.marc
|
427
447
|
- test/test_support/bad_utf_byte.utf8.marc
|
428
448
|
- test/test_support/date_resort_to_260.marc
|
449
|
+
- test/test_support/date_resort_to_264.marc
|
429
450
|
- test/test_support/date_type_r_missing_date2.marc
|
430
451
|
- test/test_support/date_with_u.marc
|
431
452
|
- test/test_support/demo_config.rb
|